Instructions to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit

SGLang

How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit with Docker Model Runner:
```
docker model run hf.co/hunterbown/Stable-DiffCoder-8B-Instruct-mlx-4Bit
```

hunterbown commited on Jan 31

Commit

414a0c3

verified ·

1 Parent(s): c42dd2b

Upload modeling_seed_diffcoder.py with huggingface_hub

Browse files

Files changed (1) hide show

modeling_seed_diffcoder.py +30 -0

modeling_seed_diffcoder.py ADDED Viewed

	@@ -0,0 +1,30 @@

+ # Copyright (c) 2026 ByteDance Ltd. and/or its affiliates
+ # SPDX-License-Identifier: MIT
+from .generation_utils import generate_block
+from transformers.models.llama.modeling_llama import LlamaForCausalLM
+from transformers.generation.utils import GenerationConfig
+import torch
+class SeedDiffcoderForCausalLM(LlamaForCausalLM):
+    @torch.no_grad()
+    def generate(
+        self,
+        input_ids=None,
+        generation_config: GenerationConfig = None,
+        **kwargs,
+    ):
+        if input_ids is None:
+            raise ValueError("input_ids must be provided")
+        if generation_config is None:
+            generation_config = self.generation_config
+        prompt = input_ids
+        output_ids, nfe = generate_block(
+            model=self,
+            prompt=prompt,
+            **kwargs,
+        )
+        return output_ids